Image search refinement using facets

• US 20140006385A1
• Filed: 06/28/2012
• Published: 01/02/2014
• Est. Priority Date: 06/28/2012
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Duwenhorst, Sven, Ebers, Bjoern-Ole
• Granted Patent: US 9,442,959 B2
• Time in Patent Office: Days
• US Class Current: 707/722
• CPC Class Codes: G06F 16/54 Browsing; Visualisation therefor

Abstract

One exemplary embodiment involves generating a plurality of facets and descriptors of all items available via an electronic shop service based on the images depicting each of the items. The facets that may be generated include a color facet, a shape facet, a texture facet, and/or other facets. The embodiment further involves receiving search criteria from a user that includes a number of search criteria elements. Each element of the search criteria may be represented by an image. The embodiment involves generating a search criteria descriptor based on the images received in connection with the search criteria. Additionally, the embodiment involves identifying items associated with images that correspond with the search criteria descriptor and providing the images of the identified items in a user interface.

Claims

1. A computer-implemented method comprising:

receiving, at a computing device comprising a processor, a request for a plurality of search results that correspond with at least one search image;

identifying, via the processor, a plurality of facets of the at least one search image;

determining, via the processor, the search results that correspond with the at least one search image based at least in part on the facets of the at least one search image; and

providing, from the computing device, the search results.

2. The computer-implemented method of claim 1, wherein the facets of the at least one search image comprises at least one of a color facet, a texture facet, or a shape facet.

3. The computer-implemented method of claim 2, wherein the color facet uniquely identifies a color of an object depicted in the at least one search image, the color being determined based at least in part on a color histogram computation.

4. The computer-implemented method of claim 2, wherein the texture facet uniquely identifies a texture of an object depicted in the at least one search image, the texture being determined based at least in part on a Fourier transform computation.

5. The computer-implemented method of claim 2, wherein the shape facet uniquely identifies a shape of an object depicted in the at least one search image, the shape being determined based at least in part by removing a plurality of background colors appearing in the at least one search image.

6. The computer-implemented method of claim 2, wherein the texture facet identifies a type of material comprising an object depicted in the at least one search image.

7. The computer-implemented method of claim 1, wherein each one of the search results are associated with a search result image.

8. The computer-implemented method of claim 1, wherein determining the search results that correspond with the at least one search image comprises:

identifying, via the processor, the facets of a plurality of potential search result images;

determining, via the processor, whether the facets of each one of the potential search result images correspond to at least one of the facets of the at least one search image; and

responsive to the determination that the potential search results correspond to the at least one of the facets of the at least one search image, including, via the processor, the potential search result images comprising facets that correspond with at least one of the facets of the at least one search image in the search results.

9. The computer-implemented method of claim 1, wherein the received request includes the at least one search image.

10. The computer-implemented method of claim 1, wherein the received request includes a listing of the facets of the at least one search image.

11. The computer-implemented method of claim 1, wherein the computing device is configured to access the at least one search image from a memory associated with the computing device.

12. The computer-implemented method of claim 11, further comprising:

determining, via the processor, a plurality of facets associated with each one of the search result images.

13. A system comprising:

a processor for executing instructions stored in computer-readable medium on one or more devices,

the application comprising one or more modules configured to perform the steps comprising;

generating on a first implementation, via the processor, a plurality of descriptors for images of items available via an electronic shop service;

receiving a search request, from a requesting source, that includes a search criteria comprising a plurality of images;

identifying a search criteria descriptor based at least in part on the received images;

identifying the items that correspond to the search criteria descriptor; and

providing the images associated with the identified items in a user interface to the requesting source.

14. The system of claim 13, wherein the descriptors for the images of the items available via the electronic shop service are further generated on a periodic basis.

15. The system of claim 13, wherein each descriptor is based at least in part on a plurality of facets associated with the item depicted by the image.

16. The system of claim 15, wherein the facets are associated with a plurality of attributes of the item, the attributes comprising at least one of a shape, a color, or a texture of the item.

17. The system of claim 13, wherein the items that correspond to the search criteria descriptor are identified based at least in part on determining whether the search criteria descriptor corresponds to at least a portion of an item descriptor associated with the item.

18. A non-transitory computer-readable medium on which is encoded program code, the program code comprising:

program code for receiving a request for items that satisfy a search criteria, the search criteria being defined by a plurality of criteria images;

program code for identifying a search criteria descriptor based on the criteria images;

program code for identifying the items that satisfy the search criteria based at least in part on the search criteria descriptor; and

program code providing a plurality of images that depict the identified items.

19. The non-transitory computer-readable medium of claim 18, wherein each one of the criteria images corresponds to one element of the search criteria.

20. The non-transitory computer-readable medium of claim 18, wherein the search criteria descriptor comprises a plurality of sub-descriptors, each one of the sub-descriptors corresponding to a facet of the item depicted in the criteria image.

21. The non-transitory computer-readable medium of claim 20, wherein the facet is at least one of a color facet, a shape facet, or a texture facet.

22. The non-transitory computer-readable medium of claim 18, wherein the items that satisfy the search criteria are identified based on whether a descriptor associated with the item corresponds to the search criteria descriptor.

23. The non-transitory computer-readable medium of claim 22, wherein the descriptor associated with the item is determined on at least one of an initial basis and a periodic basis.